no code implementations • 19 Sep 2023 • Ben Goertzel, Vitaly Bogdanov, Michael Duncan, Deborah Duong, Zarathustra Goertzel, Jan Horlings, Matthew Ikle', Lucius Greg Meredith, Alexey Potapov, Andre' Luiz de Senna, Hedra Seid Andres Suarez, Adam Vandervorst, Robert Werko
An introduction to the OpenCog Hyperon framework for Artificiai General Intelligence is presented.
no code implementations • 30 Mar 2022 • Jonathan Warrell, Alexey Potapov, Adam Vandervorst, Ben Goertzel
We introduce a formal meta-language for probabilistic programming, capable of expressing both programs and the type systems in which they are embedded.
1 code implementation • 1 Jun 2020 • Anatoly Belikov, Alexey Potapov
This paper introduces a new algorithm for unsupervised learning of keypoint detectors and descriptors, which demonstrates fast convergence and good performance across different datasets.
no code implementations • 10 Jul 2019 • Alexey Potapov, Anatoly Belikov, Vitaly Bogdanov, Alexander Scherbatiy
Probabilistic logic reasoning is a central component of such cognitive architectures as OpenCog.
no code implementations • 23 Jul 2018 • Sergey Rodionov, Alexey Potapov, Hugo Latapie, Enzo Fenoglio, Maxim Peterson
Person re-identification (Re-ID) is the task of matching humans across cameras with non-overlapping views that has important applications in visual surveillance.
no code implementations • 18 Jul 2018 • Alexey Potapov, Sergey Rodionov, Hugo Latapie, Enzo Fenoglio
Cross-dataset transfer learning is an important problem in person re-identification (Re-ID).
no code implementations • 10 Jul 2018 • Alexey Potapov, Sergey Rodionov, Maxim Peterson, Oleg Shcherbakov, Innokentii Zhdanov, Nikolai Skorobogatko
What frameworks and architectures are necessary to create a vision system for AGI?
no code implementations • 14 Jun 2018 • Alexey Potapov, Innokentii Zhdanov, Oleg Scherbakov, Nikolai Skorobogatko, Hugo Latapie, Enzo Fenoglio
Image and video retrieval by their semantic content has been an important and challenging task for years, because it ultimately requires bridging the symbolic/subsymbolic gap.
no code implementations • 4 May 2016 • Alexey Potapov
Probabilistic programming is considered as a framework, in which basic components of cognitive architectures can be represented in unified and elegant fashion.
no code implementations • 3 Aug 2013 • Alexey Potapov, Sergey Rodionov
We assume that generalized states of the world are valuable - not rewards themselves, and propose an extension of AIXI, in which rewards are used only to bootstrap hierarchical value learning.
no code implementations • 6 Jun 2013 • Sergey Rodionov, Alexey Potapov, Yurii Vinogradov
Optimal probabilistic approach in reinforcement learning is computationally infeasible.
no code implementations • 6 Jun 2013 • Alexey Potapov, Sergey Rodionov
Solomonoff induction is known to be universal, but incomputable.
no code implementations • 1 Jun 2013 • Alexey Potapov, Sergey Rodionov
Our experiments show that low-complexity induction or prediction tasks can be solved by the developed system (much more efficiently than using brute force); useful combinators can be revealed and included into the representation simplifying more difficult tasks.